TokiToki Internal
Atlas + S3
All runs
CompletedComfyUI

b8ab0468-5691-41a1-a7a9-0116d7455fc2

Queued
Jul 27, 2026, 04:15 PM
Completed
Jul 27, 2026, 04:15 PM
Execution time
22.0s
Outputs
1 · 6.2 MB
Inputs
3
Cached nodes

Outputs

1

Click an image to view it full size.

character_ref_00561_.png

node 3 · 6.2 MB

Text prompts

2
Promptnode 1 · PrimitiveStringMultiline · valueCharacter Description (your input)

Medium shot of @Aria stepping from the alley mouth into @RainStreet/Alley, moving toward the couple deeper in frame, her body tense, jaw set through the hurt, one foot forward into the wet. Drenched, hair dripping. Wardrobe: @Aria/Night-Rain, soaked. Set: inside the narrow alley now, wet brick walls close on both sides, rain pouring, the caged-lamp pool ahead with the couple just out of focus deep ahead, warm window spill. Composition: medium shot, @Aria center-right advancing, alley depth and lamp glow ahead, walls compressing. Camera: shot on ARRI Alexa 35, Signature Prime 40mm at T2.5, focus on her, alley depth soft. Lighting: cool caged-lamp spill and street glow mixing on her, deep shadow, 4:1. Color: ARRI Reveal, desaturated cool, deep blacks. Texture: wet unretouched skin, dripping hair, rain, wet brick, no smoothing. Photorealistic cinematic still, prestige crime-drama grit, 9:16.

Systemnode 2 · GeminiImageDirect · system_promptCharacter Image Generator (Nano Banana)

Generate a single, hyper-realistic character reference image (strictly no collages, text, watermarks, or borders). The image must feature a cinematic, three-quarter portrait of the described character, maintaining a sharp, tack-focused emphasis on the face with natural skin textures, pore details, and realistic micro-expressions. The lighting should be cinematic and directional (e.g., subtle split or Rembrandt lighting) to give depth, blending seamlessly with the environment specified in the character description. The character must have a natural, living presence, looking slightly off-camera or directly at the lens with a subtle, context-aware expression. Ensure the full head, neck, and upper shoulders are completely unobstructed. This image serves as a high-fidelity identity blueprint for temporal-consistent video generation.

Input media

3

Source images and video this run consumed.

character_ref_00549_.png

node 4 · 6.2 MB

character_ref_00558_.png

node 5 · 5.9 MB

character_ref_00540_.png

node 6 · 6.8 MB